Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    React code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CX
    -0.07
    TRACE
    -0.07
    EXPECTED
    -0.07
    _trace
    -0.07
    -0.07
     optimized
    -0.07
     #(
    -0.07
    GV
    -0.07
    ()?.
    -0.07
    _scan
    -0.07
    POSITIVE LOGITS
    /we
    0.08
     Holding
    0.08
     עבוד
    0.08
    ผ
    0.08
    mitting
    0.08
    Multiplicity
    0.08
    Holding
    0.08
    /D
    0.08
     Rode
    0.07
     Loading
    0.07
    Act Density 0.000%
    No Known Activations